Data-driven Localization and Estimation of Disturbance in the Interconnected Power System

Lee, Hyang-Won; Zhang, Jianan; Modiano, Eytan

doi:10.1109/smartgridcomm.2018.8587509

Cited by 5 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The large-scale deployment of Phasor Measurement Units (PMU) in recent years motivates exploring data-driven approaches for localizing transient faults [2]- [4]. In [3], the authors propose locating load increase events using logistic regression. A neural network based approach is also proposed in [4] for complementing conventional methods.…”

Section: Introductionmentioning

confidence: 99%

DeVLearn: A Deep Visual Learning Framework for Determining the Location of Temporary Faults in Power Systems

Biswas

Meyur

Centeno

2020

2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

Frequently recurring transient faults in a transmission network may be indicative of impending permanent failures. Hence, determining their location is a critical task. This paper proposes a novel image embedding aided deep learning framework called DeVLearn for faulted line location using PMU measurements at generator buses. Inspired by breakthroughs in computer vision, DeVLearn represents measurements (onedimensional time series data) as two-dimensional unthresholded Recurrent Plot (RP) images. These RP images preserve the temporal relationships present in the original time series and are used to train a deep Variational Auto-Encoder (VAE). The VAE learns the distribution of latent features in the images. Our results show that for faults on two different lines in the IEEE 68-bus network, DeVLearn is able to project PMU measurements into a two-dimensional space such that data for faults at different locations separate into well-defined clusters. This compressed representation may then be used with off-theshelf classifiers for determining fault location. The efficacy of the proposed framework is demonstrated using local voltage magnitude measurements at two generator buses.

show abstract

Section: Introductionmentioning

confidence: 99%

DeVLearn: A Deep Visual Learning Framework for Determining the Location of Temporary Faults in Power Systems

Biswas

Meyur

Centeno

2020

2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)

View full text Add to dashboard Cite

show abstract

Suppressing unknown disturbances to dynamical systems using machine learning

Restrepo,

Byers,

Skardal

2024

Commun Phys

View full text Add to dashboard Cite

Identifying and suppressing unknown disturbances to dynamical systems is a problem with applications in many different fields. Here we present a model-free method to identify and suppress an unknown disturbance to an unknown system based only on previous observations of the system under the influence of a known forcing function. We find that, under very mild restrictions on the training function, our method is able to robustly identify and suppress a large class of unknown disturbances. We illustrate our scheme with the identification of both deterministic and stochastic unknown disturbances to an analog electric chaotic circuit and with numerical examples where a chaotic disturbance to various chaotic dynamical systems is identified and suppressed.

show abstract

Locating line and node disturbances in networks of diffusively coupled dynamical agents

2021

View full text Add to dashboard Cite

A wide variety of natural and human-made systems consist of a large set of dynamical units coupled into a complex structure. Breakdown of such systems can have a dramatic impact, as in the case of neurons in the brain or lines in an electric grid, to name but a few. Preventing such catastrophic events requires in particular to be able to detect and locate the source of disturbances as fast as possible. We propose a simple method to identify and locate disturbances in networks of coupled dynamical agents, relying only on time series measurements and on the knowledge of the (possibly Kron-reduced) network structure. The strength and the appeal of the present approach lies in its simplicity paired with the ability to precisely locate disturbances and even to differentiate between line and node disturbances. If we have access to measurement at only a subset of nodes, our method is still able to identify the location of the disturbance if the disturbed nodes are measured. If not, we manage to identify the region of the network where the disturbance occurs.

show abstract

Data-driven Localization and Estimation of Disturbance in the Interconnected Power System

Cited by 5 publications

References 20 publications

DeVLearn: A Deep Visual Learning Framework for Determining the Location of Temporary Faults in Power Systems

DeVLearn: A Deep Visual Learning Framework for Determining the Location of Temporary Faults in Power Systems

Suppressing unknown disturbances to dynamical systems using machine learning

Locating line and node disturbances in networks of diffusively coupled dynamical agents

Contact Info

Product

Resources

About